A comparison and analysis of models for event trigger detection

Interpreting event mentions in text is central to many tasks from scientific research to intelligence gathering. We present an event trigger detection system and explore baseline configurations. Specifically, we test whether it is better to use a single multi-class classifier or separate binary classifiers for each label. The results suggest that binary SVM classifiers outperform multi-class maximum entropy by 6.4 points F-score. Brown cluster and WordNet features are complementary with more improvement from WordNet features.